Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.5164. Min Act: -0.1700
Data Index: 6997802 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.4227. Min Act: -0.1700
Data Index: 5735985 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.2664. Min Act: -0.1700
Data Index: 2341218 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.2039. Min Act: -0.1700
Data Index: 5310297 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.1727. Min Act: -0.1700
Data Index: 6340869 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.1414. Min Act: -0.1700
Data Index: 2439189 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.1414. Min Act: -0.1700
Data Index: 2256604 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.0476. Min Act: -0.1700
Data Index: 632197 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.0164. Min Act: -0.1700
Data Index: 8559921 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.0164. Min Act: -0.1700
Data Index: 3954957 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.0164. Min Act: -0.1700
Data Index: 174375 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5164. Min Range: -4.5164
Max Act: 4.0164. Min Act: -0.1700
Data Index: 8735633 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5164. Min Range: -4.5164
Max Act: 3.9851. Min Act: -0.1700
Data Index: 8294264 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5164. Min Range: -4.5164
Max Act: 3.9851. Min Act: -0.1700
Data Index: 8688331 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5164. Min Range: -4.5164
Max Act: 3.9851. Min Act: -0.1700
Data Index: 7229925 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5164. Min Range: -4.5164
Max Act: 3.9851. Min Act: -0.1700
Data Index: 1111508 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5164. Min Range: -4.5164
Max Act: 3.9538. Min Act: -0.1700
Data Index: 4192076 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5164. Min Range: -4.5164
Max Act: 3.9226. Min Act: -0.1700
Data Index: 7200851 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5164. Min Range: -4.5164
Max Act: 3.8913. Min Act: -0.1700
Data Index: 1351409 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5164. Min Range: -4.5164
Max Act: 3.8913. Min Act: -0.1700
Data Index: 3150010 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19